Parallel projection z-buffer images are precomputed for a number of preset viewing directions on the unit sphere. Using the depth information, we can reconstruct a 3-D point from e...
In this article we present the integration of 3-D shape knowledge into a variational model for level set based image segmentation and contour based 3-D pose tracking. Given the sur...
We describe the design and evaluation of CamWorks, a system that employs a video camera as a means of supporting capture from paper sources during reading and writing. The user ca...
William M. Newman, Christopher R. Dance, Alex S. T...
Abstract. While face recognition from a single still image has been extensively studied over a decade, face recognition based on more than one still image, such as multiple still i...
To bridge the gap between the high resolution digital images and limited display capability of mobile devices, this paper proposes a method to automatically transform static image...